Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     суток
    0.52
    bandit
    0.49
     lucro
    0.48
     sudut
    0.48
    balik
    0.46
    0.46
     Shui
    0.46
     (
    0.45
     Yaad
    0.44
     crecimiento
    0.44
    POSITIVE LOGITS
    ၉
    0.50
     একট
    0.46
    นั่ง
    0.46
    ラベル
    0.45
    勻
    0.45
    蓉
    0.45
    lains
    0.44
     यूनाइटेड
    0.44
     ይሰ
    0.43
    经
    0.43
    Act Density 0.000%

    No Known Activations